A Machine Learning Application Based in Random Forest for Integrating Mass Spectrometry-Based Metabolomic Data: A Simple Screening Method for Patients With Zika Virus.

Recent Zika outbreaks in South America, accompanied by unexpectedly severe clinical complications have brought much interest in fast and reliable screening methods for ZIKV (Zika virus) identification. Reverse-transcriptase polymerase chain reaction (RT-PCR) is currently the method of choice to detect ZIKV in biological samples. This approach, nonetheless, demands a considerable amount of time and resources such as kits and reagents that, in endemic areas, may result in a substantial financial burden over affected individuals and health services veering away from RT-PCR analysis. This study presents a powerful combination of high-resolution mass spectrometry and a machine-learning prediction model for data analysis to assess the existence of ZIKV infection across a series of patients that bear similar symptomatic conditions, but not necessarily are infected with the disease. By using mass spectrometric data that are inputted with the developed decision-making algorithm, we were able to provide a set of features that work as a "fingerprint" for this specific pathophysiological condition, even after the acute phase of infection. Since both mass spectrometry and machine learning approaches are well-established and have largely utilized tools within their respective fields, this combination of methods emerges as a distinct alternative for clinical applications, providing a diagnostic screening-faster and more accurate-with improved cost-effectiveness when compared to existing technologies.

Mass spectrometry for the characterization of brewing process.

Beer is a carbonated alcoholic beverage produced by fermenting ingredients containing starch, especially malted cereals, and other compounds such as water, hops and yeast. The process comprises five main steps: malting, mashing, boiling, fermentation and maturation. There has been growing interest in the subject, since there is increasing demand for beer quality aspects and beer is a ubiquitous alcoholic beverage in the world. This study is based on the manufacturing process of a Brazilian craft brewery, which is characterized by withdrawing samples during key production stages and using electrospray ionization (ESI) high-resolution mass spectrometry (HRMS), a selective and reliable technique used in the identification of substances in an expeditious and practical way. Multivariate data analysis, namely partial least squares discriminant analysis (PLS-DA) is used to define its markers. In both positive and negative modes of PLS-DA score plot, it is possible to notice differences between each stage. VIP score analysis pointed out markers coherent with the process, such as barley components ((+)-catechin), small peptide varieties, hop content (humulone), yeast metabolic compounds and, in maturation, flavoring compounds (caproic acid, glutaric acid and 2,3-butanediol). Besides that, it was possible to identify other important substances such as off-flavor precursors and other different trace compounds, according to the focus given. This is an attractive alternative for the control of food and beverage industry, allowing a quick assessment of process status before it is finished, preventing higher production costs, ensuring quality and helping the control of desirable features, as flavor, foam stability and drinkability. Covering different classes of compounds, this approach suggests a novel analytical strategy: "processomics", aiming at understanding processes in detail, promoting control and being able to make improvements.