Use of color based chromatographic images obtained from comprehensive two-dimensional gas chromatography in authentication analyses.

Comprehensive two-dimensional gas chromatography (GC×GC) has been an important technique used to acquire as much information as possible from a wide variety of samples. Qualitative contour plots analysis provides useful information and in daily use it ends up being handled as images of the volatile organic compounds by analysts. Cachaça samples are used in this paper to showcase the use of two-dimensional chromatographic images as the main source for authentication purposes through one-class classifiers, such as data-driven soft independent modeling of class analogy (DD-SIMCA). The proposed workflow summarizes this fast and easy process, which can be used to certify a specific brand in comparison to other brands, as well as to authenticate if samples have been adulterated. Lower quality cachaças, non-aged cachaças and cachaças aged in different wooden barrels were tested as adulterants. Chromatographic images allowed for the distinction of all brands and nearly every adulteration tested. Sensitivity was estimated at 100% for all models and specificity ranged from 96% to 100%. Different approaches were used, alternating from working with whole-sized images to working with smaller resized versions of those images. Resized chromatographic images could be potentially useful to easily compensate for slight chromatographic misalignments, allowing for faster calculations and the use of simpler software. Reductions to 50% and 25% of the original size were tested and the results did not greatly differ from whole images model. As such, 2D chromatographic images have been found to be an interesting form of evaluating a product's authenticity.

Portable NIR spectrometer for quick identification of fat bloom in chocolates.

Cocoa butter provides desirable sensory properties to chocolates; however, the exposure of chocolate to temperature variations during transportation and/or storage can lead to changes in the polymorphic form of butter, with the appearance of a dull-white film on the chocolate surface, known as fat bloom. This study investigated the use of a portable NIR spectrometer combined with chemometric tools to discriminate milk chocolate, white chocolate, 40% cocoa chocolate, and 70% cocoa chocolate samples, which were subjected to temperature abuse for 6 hours. The PCA allowed separating the samples into three classes: control at 20 °C, chocolate subjected to 35 °C, and chocolate subjected to 40 °C, for each type of chocolate studied. The PLS-DA models provided sensibility, specificity, and accuracy values in the range of 80 to 100%, and allowed identifying the wavelengths associated with the different chocolates that most impacted the construction of the models.

Evaluation of the acidic strengths on electronic ground and excited states of proton transfer dye using Excitation-Emission fluorescence matrix (EEM) and Multivariate Curve Resolution with Alternating Least Squares (MCR-ALS).

Multivariate Curve Resolution with Alternating Least Squares (MCR-ALS) was for the first time successfully used to evaluate an intricate photophysical behavior, where deprotonation on the electronic ground state (S0), intra and intermolecular proton transfer processes (ESPT and ESIPT) on the electronic excited state (S1) can simultaneously be presented. In this sense, the organic dye 2-(2'-hydroxyphenyl)benzothiazole (HBT) was used as a proof-of-concept model, where MCR-ALS showed to be a powerful tool for discriminate chemical reactions that occur concomitantly on different potential energy surfaces, which include photochemical reactions. As a result, the chemometric method showed to be a straightforward approach for the determination of the acidic strengths of those equilibria were estimated as 8.61 and 1.11 to hydroxyl deprotonation on electronic ground and excited states, respectively.

Authentication and identification of adulterants in virgin coconut oil using ATR/FTIR in tandem with DD-SIMCA one class modeling.

This study evaluates the use of Fourier transform infrared spectroscopy with attenuated total reflectance (ATR/FTIR) in tandem with data driven soft independent modeling of class analogy (DD-SIMCA) to check authenticity and monitor virgin coconut oil adulteration. By using infrared spectra of pure samples and samples adulterated with canola, corn, sunflower and soybean, one class models were developed to evaluate the authenticity and adulteration of virgin coconut oil. The proposed methodology was able to confirm the authenticity and to detect the adulteration with all tested oils in a concentration range of 10-40%. Also, it was possible to identify the four adulterants oils studied with 88-100% of sensitivity and 96-100% of specificity. The results indicated that ATR/FTIR spectroscopy in conjunction with a one-class strategy based on DD-SIMCA is a clean and fast methodology that can be easily implemented for virgin coconut oil purity control.

Colloidal gold clusters formation and chemometrics for direct SERS determination of bioanalytes in complex media.

In this work, we report the sensitive and selective sensing of the purine bases adenine and guanine in urine matrix by using surface-enhanced Raman spectroscopy (SERS) and a colloidal SERS substrate. To identify suitable conditions for quantitative analysis, the pH dependence of spectra of adenine, guanine, urine simulant and their mixtures was studied on gold nanoparticles suspension. Interestingly, although the urine matrix promotes the analytes signal suppression and overlapping bands, it can also cause an improvement in repeatability of the SERS measurements. This effect was associated to the relatively controlled formation of small-sized gold clusters and it was investigated both experimentally and theoretically. Furthermore, a correlation constrained multivariate curve resolution-alternating least squares (MCR-ALS) method was developed to resolve overlapping SERS bands and to quantify physiologically relevant (micromolar) concentrations of the bioanalytes. The performance of the proposed MCR-ALS approach (assessed in terms of figures of merit) was similar to that obtained by using partial least squares regression, but with the additional advantage of retrieving valuable spectral information. Therefore, this method can be used for improving selectivity of colloidal clusters in qualitative and quantitative SERS analysis of complex media, avoiding the need for tedious nanoparticle-surface modification or preliminary chromatographic separation.

Paper-based SERS substrate and one-class classifier to monitor thiabendazole residual levels in extracts of mango peels.

The assessment of pesticide residue levels demands fast, low cost and easy-to-use procedures which are not found in conventional methods. In this work, SERS substrates based on the deposition of gold nanoparticles (GNPs) on common office paper were prepared using a wax printer. These substrates combined with Data Driven Soft Independent Modelling of Class Analogies (DD-SIMCA), a one-class classifier algorithm, were used for detection of pesticide residues in water extracts of mango peels. Paper-based substrates made sample collection easier compared with conventional SERS methods, since few microliters of the pesticide aqueous extract from fruit peels needed to be deposited onto the substrate. Moreover, one-class classifiers dismiss the need for quantification or calibration curves. Classification of a fruit with residue levels in accordance to regulatory bodies' limits is based on a mathematical threshold. Just as in an authentication problem, all the possibilities for a given analysed fruit are now restricted to agreeing or not agreeing with current regulations. The performance of the one-class model was demonstrated by detecting thiabendazole (TBZ) residues at various mango samples, with all results being confirmed by HPLC-DAD analysis. The final model could distinguish samples with TBZ levels above the ones allowed by the Brazilian Health Regulatory Agency with 94% of selectivity and 92% of sensitivity, even in the presence of other pesticides.

Genetic fingerprinting of the Brazilian medicinal plant Chrysobalanus icaco L. (Chrysobalanaceae)

Chrysobalanus icaco L. (Chrysobalanaceae) is a medicinal species widely used in Brazil mainly to treat diabetes. Despite the medicinal importance of C. icaco, genetic information of this genus remains limited. Thus, our aim was to evaluate the influence of the genetic basis of C. icaco by determining its chemotypes. 25 C. icaco genotypes were collected from 15 sites in Belém, Marajó and Northeastern mesoregions of Pará state, Brazil. The genotypes were selected by evaluating the plant morphological characteristics such as fruit color and plant habit. The DNA fingerprinting profile was performed using PCR based RAPD technique and appropriate statistical methods were used. RAPD markers were used for evaluation of genetic diversity and molecular characterization of the C. icaco, using a total of 18 decamer primers. These primers produced 85 amplification products, with an average of 4.7 bands per primer and 99.2% polymorphism. The genotypes are genetically distinct, forming variable clusters in number and constitution by different methods. By the morphological characteristics considered, there is a tendency of clustering based on the color of the ripe fruit. We found the secondary metabolite content depends not on environmental condition, but rather on C. icaco genome. Therefore, it may have implications for ethnopharmacological use of the chemotypes.

Peripheral biomarkers allow differential diagnosis between schizophrenia and bipolar disorder.

Schizophrenia (SCZ) and bipolar disorder (BD) are severe mental disorders that pose important challenges for diagnosis by sharing common symptoms, such as delusions and hallucinations. The underlying pathophysiology of both disorders remains largely unknown, and the identification of biomarkers with potential to support diagnosis is highly desirable. In a previous study, we successfully discriminated SCZ and BD patients from healthy control (HC) individuals by employing proton magnetic resonance spectroscopy (1H-NMR). In this study, 1H-NMR data treated by chemometrics, principal component analysis (PCA) and supervised partial least-squares discriminant analysis (PLS-DA), provided the identification of metabolites present only in BD (as for instance the 2,3-diphospho-D-glyceric acid, N-acetyl aspartyl-glutamic acid, monoethyl malonate) or only in SCZ (as isovaleryl carnitine, pantothenate, mannitol, glycine, GABA). This may represent a set of potential biomarkers to support the diagnosis of these mental disorders, enabling the discrimination between SCZ and BD, and among these psychiatric patients and HC (as 6-hydroxydopamine was present in BD and SCZ but not in HC). The presence or absence of these metabolites in blood allowed the categorization of 182 independent subjects into one of these three groups. In addition, the presented data suggest disturbances in metabolic pathways in SCZ and BD, which may provide new and important information to support the elucidation and/or new insights into the neurobiology underlying these mental disorders.

Random forest as one-class classifier and infrared spectroscopy for food adulteration detection.

This paper proposes the use of random forest for adulteration detection purposes, combining the random forest algorithm with the artificial generation of outliers from the authentic samples. This proposal was applied in two food adulteration studies: evening primrose oils using ATR-FTIR spectroscopy and ground nutmeg using NIR diffuse reflectance spectroscopy. The primrose oil was adulterated with soybean, corn and sunflower oils, and the model was validated using these adulterated oils and other different oils, such as rosehip and andiroba, in pure and adulterated forms. The ground nutmeg was adulterated with cumin, commercial monosodium glutamate, soil, roasted coffee husks and wood sawdust. For the primrose oil, the proposed method presented superior performance than PLS-DA and similar performance to SIMCA and for the ground nutmeg, the random forest was superior to PLS-DA and SIMCA. Also, in both applications using the random forest, no sample was excluded from the external validation set.

Rapid Determination of Nutritional Parameters of Pasta/Sauce Blends by Handheld Near-Infrared Spectroscopy.

Nowadays, near infrared (NIR) spectroscopy has experienced a rapid progress in miniaturization (instruments < 100 g are presently available), and the price for handheld systems has reached the < $500 level for high lot sizes. Thus, the stage is set for NIR spectroscopy to become the technique of choice for food and beverage testing, not only in industry but also as a consumer application. However, contrary to the (in our opinion) exaggerated claims of some direct-to-consumer companies regarding the performance of their "food scanners" with "cloud evaluation of big data", the present publication will demonstrate realistic analytical data derived from the development of partial least squares (PLS) calibration models for six different nutritional parameters (energy, protein, fat, carbohydrates, sugar, and fiber) based on the NIR spectra of a broad range of different pasta/sauce blends recorded with a handheld instrument. The prediction performance of the PLS calibration models for the individual parameters was double-checked by cross-validation (CV) and test-set validation. The results obtained suggest that in the near future consumers will be able to predict the nutritional parameters of their meals by using handheld NIR spectroscopy under every-day life conditions.

Evaluation of miscibility and polymorphism of synthetic and natural lipids for nanostructured lipid carrier (NLC) formulations by Raman mapping and multivariate curve resolution (MCR).

Nanostructured lipid carriers (NLC) belong to youngest lipid-based nanocarrier class and they have gained increasing attention over the last ten years. NLCs are composed of a mixture of solid and liquid lipids, which solubilizes the active pharmaceutical ingredient, stabilized by a surfactant. The miscibility of the lipid excipients and structural changes (polymorphism) play an important role in the stability of the formulation and are not easily predicted in the early pharmaceutical development. Even when the excipients are macroscopically miscible, microscopic heterogeneities can result in phase separation during storage, which is only detected after several months of stability studies. In this sense, this work aimed to evaluate the miscibility and the presence of polymorphism in lipid mixtures containing synthetic (cetyl palmitate, Capryol 90®, Dhaykol 6040 LW®, Precirol ATO5® and myristyl myristate) and natural (beeswax, cocoa and shea butters, copaiba, sweet almond, sesame and coconut oils) excipients using Raman mapping and multivariate curve resolution - alternating least squares (MCR-ALS) method. The results were correlated to the macroscopic stability of the formulations. Chemical maps constructed for each excipient allowed the direct comparison among formulations, using standard deviation of the histograms and the Distributional Homogeneity Index (DHI). Lipid mixtures of cetyl palmitate/Capryol®; cetyl palmitate/Dhaykol®; myristyl myristate/Dhaykol® and myristyl myristate/coconut oil presented a single histogram distribution and were stable. The sample with Precirol®/Capryol® was not stable, although the histogram distribution was narrower than the samples with cetyl palmitate, indicating that miscibility was not the factor responsible for the instability. Structural changes before and after melting were identified for cocoa butter and shea butter, but not in the beeswax. Beeswax + copaiba oil sample was very homogenous, without polymorphism and stable over 6 months. Shea butter was also homogeneous and, in spite of the polymorphism, was stable. Formulations with cocoa butter presented a wider histogram distribution and were unstable. This paper showed that, besides the miscibility evaluation, Raman imaging could also identify the polymorphism of the lipids, two major issues in lipid-based formulation development that could help guide the developer understand the stability of the NLC formulations.

Insights into the Effects of Crack Abuse on the Human Metabolome Using a NMR Approach.

Approximately 255 million people consume illicit drugs every year, among which 18 million use cocaine. A portion of this drug is represented by crack, but it is difficult to estimate the number of users since most are marginalized. However, there are no recognized efficacious pharmacotherapies for crack-cocaine dependence. Inflammation and infection in cocaine users may be due to behavior adopted in conjunction with drug-related changes in the brain. To understand the metabolic changes associated with the drug abuse disorder and identify biomarkers, we performed a 1H NMR-based metabonomic analysis of 44 crack users' and 44 healthy volunteers' blood serum. The LDA model achieved 98% of accuracy. From the water suppressed 1H NMR spectra analyses, it was observed that the relative concentration of lactate was higher in the crack group, while long chain fatty acid acylated carnitines were decreased, which was associated with their nutritional behavior. Analyses of the aromatic region of CPMG 1H NMR spectra demonstrated histidine and tyrosine levels increased in the blood serum of crack users. The reduction of carnitine and acylcarnitines and the accumulation of histidine in the serum of the crack users suggest that histamine biosynthesis is compromised. The tyrosine level points to altered dopamine concentration.

Green methodology for soil organic matter analysis using a national near infrared spectral library in tandem with learning machine.

Precision agriculture requires faster and automatic responses for fertility parameters, especially regarding soil organic matter (SOM). In Brazil, the standard methodology for SOM determination is a wet procedure based on the oxidation of the sample by an excess of potassium dichromate based on Walkley-Black method. This methodology has serious drawbacks, since, at a national level, generates approximately 600,000 L/year of toxic acid waste containing Cr3+ and possibly Cr6+, besides time consuming and expensive. Herein, we present a faster green methodology that can eliminate the generation of these hazardous wastes and reduces the costs of analysis by approximately 80%, democratizing the soil fertility information and increasing the productivity. The methodology is based on the use of a national near infrared spectral library with approximately 43,000 samples and learning machine data analysis based on a random forest algorithm. The methodology was validated by submitting the prediction results of 12 blind soil samples to a proficiency assay used for fertility soil laboratories qualification, receiving the maximum quality excellence index, indicating that it is suitable for use in routine analysis.

Fast discrimination of bacteria using a filter paper-based SERS platform and PLS-DA with uncertainty estimation.

Rapid and reliable identification of bacteria is an important issue in food, medical, forensic, and environmental sciences; however, conventional procedures are time-consuming and often require extensive financial and human resources. Herein, we present a label-free method for bacterial discrimination using surface-enhanced Raman spectroscopy (SERS) and partial least squares discriminant analysis (PLS-DA). Filter paper decorated with gold nanoparticles was fabricated by the dip-coating method and it was utilized as a flexible and highly efficient SERS substrate. Suspensions of bacterial samples from three genera and six species were directly deposited on the filter paper-based SERS substrates before measurements. PLS-DA was successfully employed as a multivariate supervised model to classify and identify bacteria with efficiency, sensitivity, and specificity rates of 100% for all test samples. Variable importance in projection was associated with the presence/absence of some purine metabolites, whereas confidence intervals for each sample in the PLS-DA model were calculated using a resampling bootstrap procedure. Additionally, a potential new species of bacteria was analyzed by the proposed method and the result was in agreement with that obtained via 16S rRNA gene sequence analysis, thereby indicating that the SERS/PLS-DA approach has the potential to be a valuable tool for the discovery of novel bacteria. Graphical abstract This paper describes the discrimination of bacteria at the genus and species levels, after minimal sample preparation, using paper-based SERS substrates and PLS-DA with uncertainty estimation.

Comparison of different chemometric methods to extract chemical and physical information from Raman images of homogeneous and heterogeneous semi-solid pharmaceutical formulations.

In formulations of nanostructured lipid carriers, lipid solid dispersions and self-emulsifying drug delivery systems, it is common that a solid or semi-solid lipid excipient is mixed with a liquid solvent or liquid lipid. Even when the excipients are visually miscible upon melting, they might have microscopic non-homogeneities which could lead to instability over time and future phase separation. Raman mapping associated with chemometric methods can be useful to evaluate spatial distribution of compounds, however it has not been extensively applied to the formulations mentioned above. The aim of this work was to compare the outcomes of three different chemometric methods - principal components analysis (PCA), multivariate curve resolution with alternating least squares (MCR-ALS) and independent components analysis (ICA) - to study two systems of very different degrees of microscopic miscibility: cetyl palmitate + Transcutol© (heterogeneous) and polyethylene glycol 6000 (PEG 6000) + Tween 80© (homogeneous). These two samples were chosen due to large differences in spatial distribution of the compounds over the pixels which could require different approaches for data treatment. The three methods were compared regarding recovered concentrations (or scores), signals (or loadings) and the need for matrix augmentation to obtain reliable results. Results showed that PCA loadings were the mathematical differences of the spectra of pure compounds for both samples, and therefore only 'contrast images' could be generated. MCR and ICA provided signals that could be related to the chemical components, however MCR presented rotational ambiguities even for the very heterogeneous sample, a situation in which ICA performed better as a blind search method. For the homogeneous sample, both methods showed rank deficiency and therefore the use of a matrix augmentation was necessary. ICA and PCA allowed identifying physical modifications in the homogeneous semi-solid PEG 6000/Tween 80® sample over the time, probably due to the folding/unfolding of the crystalline chains of PEG 6000. Therefore, this work discusses the ability of the three chemometrics methods to extract information from Raman spectra in order to characterize the chemical, spatial and even physical aspects of semi-solid pharmaceutical formulations, which could be of much use for stability studies of different drug delivery systems.

Surface-enhanced Raman spectroscopy and MCR-ALS for the selective sensing of urinary adenosine on filter paper.

Adenosine is a purine nucleoside that is present in all human cells and is essential for regulating certain physiological activities in tissues and organs. Since adenosine is considered to be a potential cancer biomarker in urine, its determination may be crucial for the early diagnosis and non-invasive monitoring of cancer. Herein, we present a label-free method to quantify urinary adenosine using surface-enhanced Raman spectroscopy (SERS) and multivariate curve resolution-alternating least squares (MCR-ALS). Ring-oven preconcentration and direct deposition of monodisperse gold nanoparticles on filter paper were employed to improve the sampling efficiency. Further, MCR-ALS (assessed with and without a correlation constraint), the standard addition method and pH controls were combined to compensate for the matrix effect and to address overlapping bands in the analysis of human urine samples. As a result, the proposed method showed to be sensitive (LOD varying between 3.8 and 4.9 µmol L-1, S/R = 3), reproducible (RSD less than ±â€¯15%), and selective over other nucleosides (guanosine, cytidine, thymidine and uridine) and unknown interferences (second-order advantage). This is the first report of a SERS-chemometric method applied to urinary adenosine sensing at physiologically relevant concentrations, with minimal sample preparation, and has strong potential to be a valuable tool in cancer research.

Characterization of the aroma profile of novel Brazilian wines by solid-phase microextraction using polymeric ionic liquid sorbent coatings.

In this study, a series of polymeric ionic liquid (PIL) sorbent coatings is evaluated for the extraction of polar volatile organic compounds (VOCs) from Brazilian wines using headspace solid-phase microextraction (HS-SPME), including samples from 'Isabella' and 'BRS Magna' cultivars-the latter was recently introduced by the Brazilian Agricultural Research Corporation - National Grape & Wine Research Center. The structurally tuned SPME coatings were compared to the commercial SPME phases, namely poly(acrylate) (PA) and divinylbenzene/carboxen/poly(dimethylsiloxane) (DVB/CAR/PDMS). The separation, detection and identification of the aroma profiles were obtained using comprehensive two-dimensional gas chromatography mass spectrometry (GC×GC-MS). The best performing PIL-based SPME fiber, namely 1-hexadecyl-3-vinylimidazolium bis[(trifluoromethyl)sulfonyl]imide with 1,12-di(3-vinylimidazolium)dodecane dibis[(trifluoromethyl)sulfonyl]imide incorporated cross-linker supported on an elastic nitinol wire, exhibited superior performance to DVB/CAR/PDMS regarding the average number of extracted peaks and extracted more polar analytes providing additional insight into the aroma profile of 'BRS Magna' wines. Four batches of wine were evaluated, namely 'Isabella' and 'BRS Magna' vintages 2015 and 2016, using highly selective PIL-based SPME coatings and enabled the detection of 350+ peaks. Furthermore, this is the first report evaluating the aroma of 'BRS Magna' wines. A hybrid approach that combined pixel-based Fisher ratio and peak table-based data comparison was used for data handling. This proof-of-concept experiment provided reliable and statistically valid distinction of wines that may guide regulation agencies to create high sample throughput protocols to screen wines exported by Brazilian vintners. Graphical abstract Highly selective extraction of wine aroma using polymeric ionic liquid.

Comparison of macro and micro Raman measurement for reliable quantitative analysis of pharmaceutical polymorphs.

This work reports on the use of micro- and macro-Raman measurements for quantification of mebendazole (MBZ) polymorphs A, B, and C in mixtures. Three Raman spectrophotometers were studied with a laser spot size of 3, 80 and 100 µm and spectral resolutions of 3.9, 9 and 4 cm-1, respectively. The samples studied were ternary mixtures varying the MBZ polymorphs A and C from 0 to 100% and polymorph B from 0 to 30%. Partial Least Squares (PLS) regression models were developed using the pre-processing spectra (2nd derivative) of the ternary mixtures. The best performance was obtained when the macro-Raman configuration was applied, obtaining RMSEP values of 1.68%, 1.24% and 2.03% w/w for polymorphs A, B, and C, respectively. In general, micro-Raman presented worst results for MBZ polymorphs prediction because the spectra obtained with this configuration does not represent the bulk proportion of mixtures, which have different particle morphologies and sizes. In addition, the influence of these particle features on micro-Raman measurements was also studied. Finally, the results demonstrated that reliable analytical quantifying of MBZ polymorphs can be reached using a laser with wider area illuminated, thus enabling acquisition of more reproductive and representative spectra of the mixtures.

Digital Protocol for Chemical Analysis at Ultralow Concentrations by Surface-Enhanced Raman Scattering.

Single molecule surface-enhanced Raman spectroscopy (SM-SERS) has the potential to revolutionize quantitative analysis at ultralow concentrations (less than 1 nM). However, there are no established protocols to generalize the application of this technique in analytical chemistry. Here, a protocol for quantification at ultralow concentrations using SM-SERS is proposed. The approach aims to take advantage of the stochastic nature of the single-molecule regime to achieved lower limits of quantification (LOQ). Two emerging contaminants commonly found in aquatic environments, enrofloxacin (ENRO) and ciprofloxacin (CIPRO), were chosen as nonresonant molecular probes. The methodology involves a multivariate resolution curve fitting known as non-negative matrix factorization with alternating least-squares algorithm (NMF-ALS) to solve spectral overlaps. The key element of the quantification is to realize that, under SM-SERS conditions, the Raman intensity generated by a molecule adsorbed on a "hotspot" can be digitalized. Therefore, the number of SERS event counts (rather than SERS intensities) was shown to be proportional to the solution concentration. This allowed the determination of both ENRO and CIPRO with high accuracy and precision even at ultralow concentrations regime. The LOQ for both ENRO and CIPRO were achieved at 2.8 pM. The digital SERS protocol, suggested here, is a roadmap for the implementation of SM-SERS as a routine tool for quantification at ultralow concentrations.

Visible and near infrared spectroscopy coupled to random forest to quantify some soil quality parameters.

This study evaluates the use of visible and near infrared spectroscopy (Vis-NIRS) combined with multivariate regression based on random forest to quantify some quality soil parameters. The parameters analyzed were soil cation exchange capacity (CEC), sum of exchange bases (SB), organic matter (OM), clay and sand present in the soils of several regions of Brazil. Current methods for evaluating these parameters are laborious, timely and require various wet analytical methods that are not adequate for use in precision agriculture, where faster and automatic responses are required. The random forest regression models were statistically better than PLS regression models for CEC, OM, clay and sand, demonstrating resistance to overfitting, attenuating the effect of outlier samples and indicating the most important variables for the model. The methodology demonstrates the potential of the Vis-NIR as an alternative for determination of CEC, SB, OM, sand and clay, making possible to develop a fast and automatic analytical procedure.