Prediction Of Fatty Acid Composition Research Articles

Prediction of fatty acid composition in intact and minced fat of European autochthonous pigs breeds by near infrared spectroscopy

The fatty acids profile has been playing a decisive role in recent years, thanks to technological, sensory and health demands from producers and consumers. The application of NIRS technique on fat tissues, could lead to more efficient, practical, and economical in the quality control. The study aim was to assess the accuracy of Fourier Transformed Near Infrared Spectroscopy technique to determine fatty acids composition in fat of 12 European local pig breeds. A total of 439 spectra of backfat were collected both in intact and minced tissue and then were analyzed using gas chromatographic analysis. Predictive equations were developed using the 80% of samples for the calibration, followed by full cross validation, and the remaining 20% for the external validation test. NIRS analysis of minced samples allowed a better response for fatty acid families, n6 PUFA, it is promising both for n3 PUFA quantification and for the screening (high, low value) of the major fatty acids. Intact fat prediction, although with a lower predictive ability, seems suitable for PUFA and n6 PUFA while for other families allows only a discrimination between high and low values.

Application of linear and machine learning models to genomic prediction of fatty acid composition in Japanese Black cattle.

We collected 3180 records of oleic acid (C18:1) and monounsaturated fatty acid (MUFA) measured using gas chromatography (GC) and 6960 records of C18:1 and MUFA measured using near-infrared spectroscopy (NIRS) in intermuscular fat samples of Japanese Black cattle. We compared genomic prediction performance for four linear models (genomic best linear unbiased prediction [GBLUP], kinship-adjusted multiple loci [KAML], BayesC, and BayesLASSO) and five machine learning models (Gaussian kernel [GK], deep kernel [DK], random forest [RF], extreme gradient boost [XGB], and convolutional neural network [CNN]). For GC-based C18:1 and MUFA, KAML showed the highest accuracies, followed by BayesC, XGB, DK, GK, and BayesLASSO, with more than 6% gain of accuracy by KAML over GBLUP. Meanwhile, DK had the highest prediction accuracy for NIRS-based C18:1 and MUFA, but the difference in accuracies between DK and KAML was slight. For all traits, accuracies of RF and CNN were lower than those of GBLUP. The KAML extends GBLUP methods, of which marker effects are weighted, and involves only additive genetic effects; whereas machine learning methods capture non-additive genetic effects. Thus, KAML is the most suitable method for breeding of fatty acid composition in Japanese Black cattle.

Prediction of fatty acid composition using milk spectral data and its associations with various mid-infrared spectral regions in Michigan Holsteins

Fatty acid composition in milk is not only reflective of nutritional quality but also potentially predictive of other attributes (e. g. including the cow's energy balance and its relative output of methane emissions). Furthermore, a higher ratio of long-chain to short-chain fatty acids or mean carbon number has been associated with negative energy balance in dairy cows, whereas enhanced nutritional properties have been generally associated with higher levels of unsaturation. We set out to directly compare Bayesian regression strategies with partial least squares for the prediction of various milk fatty acids using Fourier-transform infrared spectrum data on 777 milk samples taken from 579 cows on 4 Michigan dairy herds between 5 and 90 d in milk. We also set out to identify those spectral regions that might be associated with fatty acids and whether carbon number or level of unsaturation might contribute to the strength of these associations. These associations were based on adaptively clustered windows of wavenumbers to mitigate the distorting effects of severe multicollinearity on marginal associations involving individual wavenumbers. In general, Bayesian regression methods, particularly the variable selection method BayesB, outperformed partial least squares regression for cross-validation prediction accuracy for both individual fatty acids and fatty acid groups. Strong signals for wavenumber associations using BayesB were well distributed throughout the mid-infrared spectrum, particularly between 910 and 3,998 cm-1. Carbon number appeared to be linearly related to strength of wavenumber associations for 38 moderately to highly predicted fatty acids within the spectral regions of 2,286 to 2,376 and 2,984 to 3,100 cm-1, whereas nonlinear associations were determined within 1,141 to 1,205; 1,570 to 1,630; and 1,727 to 1,768 cm-1. However, no such associations were detected with level of unsaturation. Spectral regions where there were significant relationships between strength of association and carbon number may be useful targets for inferring the relative proportion of long-chain to short-chain fatty acids, and hence energy balance.

NIRS to assess chemical composition of sheep and goat cheese

NIRS to assess chemical composition of sheep and goat cheese

Prediction of fatty acid composition in camellia oil by 1H NMR combined with PLS regression

A rapid method for the determination of fatty acid (FA) composition in camellia oils was developed based on the 1H NMR technique combined with partial least squares (PLS) method. Outliers detection, LVs optimization and data pre-processing selection were explored during the model building process. The results showed the optimal models for predicting the content of C18:1, C18:2, C18:3, saturated, unsaturated, monounsaturated and polyunsaturated FA were achieved by Pareto scaling (Par) pretreatment, with correlation coefficient (R2) above 0.99, the root mean square error of estimation and prediction (RMSEE, RMSEP) lower than 0.954 and 0.947, respectively. Mean-centering (Ctr) was more suitable for the model of C16:0 and C18:0 with the best performance indicators (R2 ≥ 0.945, RMSEE ≤ 0.377, RMSEP ≤ 0.212). This study indicated that 1H NMR has the potential to be applied as a rapid and routine method for the analysis of FA composition in camellia oils.

Prediction of fatty acid composition of sunflower seeds by near-infrared reflectance spectroscopy.

This study was performed in order to evaluate efficiency of near-infrared reflectance spectroscopy (NIRS) for the determination of fatty acid composition ratio of sunflower seeds and to compare performance of calibration methods. Calibration equations were developed using modified partial least squares (MPLS) and partial least squares (PLS) regression methods. Ninety-three sunflower seed varieties were from test field of East Mediterranean Agricultural Research Institute. In order to determine the reference fatty acid values needed to construct calibration in NIRS analysis, sunflower seed samples were analyzed by gas chromatography method. Coefficients of determination (R2) in calibration were developed using MPLS and PLS as follows: for palmitic acid 0.706-0.664, for stearic acid 0.615-0.654, for oleic acid 0.996-0.994, for linoleic acid 0.995-0.994, for arachidic acid 0.768-0.643, for linolenic acid 0.818-0.763, for behenic acid 0.891-0.776, for eicosapentaenoic 0.933-0.892, for unsaturated fatty acid 0.837-0.890 and for saturated fatty acid 0.837-0.890 respectively. The results showed that NIRS was a reliable technique that can be used as a tool for rapid pre-screening of fatty acid composition of sunflower seeds.

Whole-genome prediction of fatty acid composition in meat of Japanese Black cattle.

Because fatty acid composition influences the flavor and texture of meat, controlling it is particularly important for cattle breeds such as the Japanese Black, characterized by high meat quality. We evaluated the predictive ability of single-step genomic best linear unbiased prediction (ssGBLUP) in fatty acid composition of Japanese Black cattle by assessing the composition of seven fatty acids in 3088 cattle, of which 952 had genome-wide marker genotypes. All sires of the genotyped animals were genotyped, but their dams were not. Cross-validation was conducted for the 952 animals. The prediction accuracy was higher with ssGBLUP than with best linear unbiased prediction (BLUP) for all traits, and in an empirical investigation, the gain in accuracy of using ssGBLUP over BLUP increased as the deviations in phenotypic values of the animals increased. In addition, the superior accuracy of ssGBLUP tended to be more evident in animals whose maternal grandsire was genotyped than in other animals, although the effect was small.

Rapid prediction of fatty acid composition of vegetable oil by Raman spectroscopy coupled with least squares support vector machines

The fatty acid composition of vegetable oil plays a significant role in a nutrition‐balanced diet, which makes this industry more quality conscious. A set of store‐purchased vegetable oils and their binary mixtures were characterized by Raman spectra in a region of 800–2000 cm−1. The obtained Raman spectral data were pretreated, and intensities of eight characteristic peaks were extracted as the eigenvalues of an entire spectrum. A prediction model of fatty acid content based on least squares support vector machines (LS‐SVM) were established for multivariate analysis between the Raman spectral eigenvalues and the fatty acid composition measured by gas chromatography (GC) method. The performance of the model was evaluated by comparing the predicted values to the reference values from GC analysis. The correlation coefficient for the prediction of oleic acid, linoleic acid and α‐linolenic acid was 0.9972, 0.9982 and 0.9854, respectively. Raman spectroscopy based on LS‐SVM can be a promising technique for predicting the fatty acid composition of vegetable oil with the advantages of being simple and time‐effective while not requiring any sample preprocessing. In particular, a portable Raman system is suitable for on‐site detection in practical applications. Copyright © 2013 John Wiley & Sons, Ltd.

Prediction of fatty acid composition in Camellia oleifera oil by near infrared transmittance spectroscopy (NITS)

Under the serious circumstances of Camellia oleifera adulteration, the accurate examination for quality trait of C. oleifera oil is extremely urgent. For rapid determination of FA composition in C. oleifera oil, the feasibility of NITS was first studied. The quantitative models for FA were built based on PLS regression. NITS spectra is able to accurately predict for oleic, linoleic, and palmitic acids (Rcv>0.844, R2>0.886). Rcv are 0.91987, 0.95755, and 0.84447, and R2 are 0.9424, 0.9682, 0.8862 for NITS models of oleic, linoleic, and palmitic acids, respectively. But models for stearic and unsaturated acids are less accurate, with values of Rcv from 0.67440 to 0.69114, and R2 from 0.6834 to 0.7587. These results indicate that NITS will have potential to be used in predicting FA composition of C. oleifera oil.

Prediction of fatty acid composition of vegetable oils based on rheological measurements using nonlinear models

AbstractThe aim of this study was to model the fatty acid composition of vegetable oils by using the adaptive neuro fuzzy inference system (ANFIS) and artificial neural network (ANN) based on rheological measurements. For this aim, seven different refined vegetable oils (hazelnut, soybean, sunflower, olive, canola, corn, and cotton seed) were used. Olive oil had the highest viscosity value of 0.067 Pa s. Principal component analysis (PCA) was performed to determine the correlations among the fatty acids of the oils to reduce parameters which were modeled. PC1 composed of C18:0, C18:1, C18:2, and C20:0 as PC2 composed of C16:0, C18:3, and C22:0. After determination of the fatty acid composition and the rheological properties of the oils, ANN and ANFIS models were established. The inputs were selected as oil type, shear rate and shear stress and the outputs were C16:0 and C18:2. The root mean square error (RMSE), mean absolute error (MAE), and determination coefficient (R2) were used for testing the accuracy of the models. This comparison showed that ANFIS and ANN achieved a satisfactory prediction for fatty acid composition of the vegetable oils studied and ANFIS is better than ANN.Practical applications: Determination of the fatty acid composition of vegetable oils is important for the assessment of the purity of the oils as well as the nutritional quality. The fatty acid composition of the oils affects their rheological characteristics. Rheological measurements are easier than chromatographic analysis. Therefore, we aimed to establish a model for prediction of the fatty acid composition of the oils based on their rheological behaviors.

Prediction of fatty acid composition using a NIRS fibre optics probe at two different locations of ham subcutaneous fat

Abstract NIR technology was used to analyze the fatty acid composition of fat tissue from conjugated linoleic acid fed pigs by direct application of a fibre optics probe on two different locations of subcutaneous fat. One hundred and fifty-three pigs were fed three different diets and the fatty acid profile of subcutaneous fat from Gluteus medius was analyzed using gas chromatography and FT-NIR in a longitudinal and transversal cut. Spectra were acquired using a Bruker Optics Matrix-F duplex spectrometer equipped with a fibre optics probe (IN-268-2). Total saturated, monounsaturated and polyunsaturated together as well as oleic and stearic fatty acids were predicted accurately (R2 > 0.70), myristic, and linoleic fatty acids were predicted with lower accuracy (0.60

Prediction of fatty acid composition of fresh and freeze-dried cheeses by visible–near-infrared reflectance spectroscopy

Visible–near-infrared reflectance spectroscopy was used to predict the fatty acid (FA) composition of 445 cows’ and goats’ fresh and freeze-dried cheeses. The FA composition of samples was analysed by reference method. Samples were scanned (400–2500 nm) and predictive equations were developed using modified partial least squares with both cross-validation and external validation. The coefficient of determination in external validation (R 2V) and residual predictive deviation in the validation set (RPDV) were good for total saturated (0.89, 2.84), monounsaturated (0.90, 2.90), polyunsaturated (0.88, 2.54), trans (0.92, 3.24) FA, butyric (0.84, 2.43), capric (0.92, 2.96), myristic (0.89, 2.94), palmitic (0.91, 3.32), vaccenic (0.88, 2.63), and rumenic (0.90, 2.70) acids in fresh cheeses. Approximate or poor predictions were obtained for caproic, caprylic, lauric, stearic, oleic, linoleic, and linolenic acids (R 2V⩽0.80; RPDV⩽2.08). The quantification was significantly more accurate for caprilic, capric, and linoleic acids with freeze-dried cheeses compared with fresh cheeses.

Effect of vitamin C addition to ground beef from grass-fed or grain-fed sources on color and lipid stability, and prediction of fatty acid composition by near-infrared reflectance analysis

Research was conducted to determine the effect of postmortem vitamin C addition (VITC) versus no VITC (CONTROL) to ground beef from grass-fed (GRASS) or grain-fed (GRAIN) sources on color and lipid stability during 8 days of illuminated display at 4 °C. The use of near-infrared reflectance (NIR) spectroscopy to predict the fatty acid composition of ground beef and its potential to discriminate samples from different nutritional backgrounds were also evaluated. Total lipid content of ground beef was 53% lower ( P<0.05) for GRASS than GRAIN. Ground beef from GRASS had greater ( P<0.01) percentages of saturated (SFA) and polyunsaturated (PUFA) fatty acids, and lower ( P<0.01) percentages of monounsaturated (MUFA) fatty acids than GRAIN. For GRAIN, VITC reduced ( P<0.01) lipid oxidation, and resulted in darker ( P<0.01) and redder ( P<0.01) color of the ground beef from 2 to 8 days of display compared to CONTROL. For GRASS, lipid oxidation did not differ ( P>0.05) for VITC and CONTROL. VITC improved ( P<0.01) color stability by prolonging more red color in GRASS during 8 days of display. Results from partial least squares modeling showed accurate predictions using NIR for total saturated [standard error of performance (SEP=1.16%), coefficient of determination on the validation set ( r 2=0.87)] and unsaturated (SEP=1.18% and r 2=0.90) fatty acid contents of ground beef, as well as the composition of stearic, oleic, and linolenic (SEP=1.2%, 1.27%, and 0.07%; r 2=0.91, 0.92, and 0.93, respectively). However, the composition of other individual fatty acids was poorly predicted. VITC was effective in retarding pigment oxidation in ground beef from both GRAIN and GRASS; however, VITC reduced lipid oxidation in GRAIN samples only, despite higher PUFA percentages in GRASS. NIR can be used to predict accurately the content of total saturated and unsaturated, and stearic, oleic, and linolenic fatty acids in ground beef. NIR showed potential to discriminate meat samples originating from different feeding production systems.