Classification-based machine learning approaches to predict the taste of molecules: A review.

The capacity to discriminate safe from dangerous compounds has played an important role in the evolution of species, including human beings. Highly evolved senses such as taste receptors allow humans to navigate and survive in the environment through information that arrives to the brain through electrical pulses. Specifically, taste receptors provide multiple bits of information about the substances that are introduced orally. These substances could be pleasant or not according to the taste responses that they trigger. Tastes have been classified into basic (sweet, bitter, umami, sour and salty) or non-basic (astringent, chilling, cooling, heating, pungent), while some compounds are considered as multitastes, taste modifiers or tasteless. Classification-based machine learning approaches are useful tools to develop predictive mathematical relationships in such a way as to predict the taste class of new molecules based on their chemical structure. This work reviews the history of multicriteria quantitative structure-taste relationship modelling, starting from the first ligand-based (LB) classifier proposed in 1980 by Lemont B. Kier and concluding with the most recent studies published in 2022.

Effect of Sprouting on Proteins and Starch in Quinoa (Chenopodium quinoa Willd.).

This study aims at understanding the relation among sprouting time (from 12 up to 72 h), changes in protein and starch components, and flour functionality in quinoa. Changes related to the activity of sprouting-related proteases were observed after 48 h of sprouting in all protein fractions. Progressive proteolysis resulted in relevant modification in the organization of quinoa storage proteins, with a concomitant increase in the availability of physiologically relevant metals such as copper and zinc. Changes in the protein profile upon sprouting resulted in improved foam stability, but in impaired foaming capacity. The increased levels of amylolytic enzymes upon sprouting also made starch less prompt to gelatinize upon heating. Consequently, starch re-association in a more ordered structure upon cooling was less effective, resulting in low setback viscosity. The nature and the intensity of these modifications suggest various possibilities as for using flour from sprouted quinoa as an ingredient in the formulation of baked products.

Quinoa bitterness: causes and solutions for improving product acceptability.

Awareness of the several agronomic, environmental, and health benefits of quinoa has led to a constant increase in its production and consumption not only in South America, where it is a native crop, but also in Europe and the USA. However, producing wheat or gluten-free based products enriched with quinoa alters some quality characteristics, including sensory acceptance. Several anti-nutritional factors such as saponins are concentrated in the grain pericarp. These bitter and astringent substances may interfere with the digestion and absorption of various nutrients. Developing processes to decrease or modify the bitterness of quinoa can enhance palatability, and thus consumption, of quinoa. In addition to the production of sweet varieties of quinoa, other processes have been proposed. Some of them (i.e. washing, pearling and the combination of the two) have a direct effect on saponins, either by solubilization and/or the mechanical removal of seed layers. Others, such as fermentation or germination, are able to mask the bitterness with aroma compounds and/or sugar formation. This review presents the major sources of the undesirable sensory attributes of quinoa, including bitterness, and various ways of counteracting the negative characteristics of quinoa. © 2018 Society of Chemical Industry.