Classification and Prediction by Pigment Content in Lettuce (Lactuca sativa L.) Varieties Using Machine Learning and ATR-FTIR Spectroscopy

Green or purple lettuce varieties produce many secondary metabolites, such as chlorophylls, carotenoids, anthocyanins, flavonoids, and phenolic compounds, which is an emergent search in the field of biomolecule research. The main objective of this study was to use multivariate and machine learning algorithms on Attenuated Total Reflectance Fourier Transform Infrared Spectroscopy (ATR-FTIR)-based spectra to classify, predict, and categorize chemometric attributes. The cluster heatmap showed the highest efficiency in grouping similar lettuce varieties based on pigment profiles. The relationship among pigments was more significant than the absolute contents. Other results allow classification based on ATR-FTIR fingerprints of inflections associated with structural and chemical components present in lettuce, obtaining high accuracy and precision (>97%) by using principal component analysis and discriminant analysis (PCA-LDA)-associated linear LDA and SVM machine learning algorithms. In addition, PLSR models were capable of predicting Chla, Chlb, Chla+b, Car, AnC, Flv, and Phe contents, with R2P and RPDP values considered very good (0.81−0.88) for Car, Anc, and Flv and excellent (0.91−0.93) for Phe. According to the RPDP metric, the models were considered excellent (>2.10) for all variables estimated. Thus, this research shows the potential of machine learning solutions for ATR-FTIR spectroscopy analysis to classify, estimate, and characterize the biomolecules associated with secondary metabolites in lettuce.

Cell wall structure and composition is affected by light quality in tomato seedlings

Light affects many aspects of cell development. Tomato seedlings growing at different light qualities (white, blue, green, red, far-red) and in the dark displayed alterations in cell wall structure and composition. A strong and negative correlation was found between cell wall thickness and hypocotyl growth. Cell walls was thicker under blue and white lights and thinner under far-red light and in the dark, while intermediate values was observed for red or green lights. Additionally, the inside layer surface of cell wall presented random deposited microfibrillae angles under far-red light and in the dark. However, longitudinal transmission electron microscopy indicates a high frequency of microfibrils close to parallels related to the elongation axis in the outer layer. This was confirmed by ultra-high resolution small angle X-ray scattering. These data suggest that cellulose microfibrils would be passively reoriented in the longitudinal direction. As the cell expands, the most recently deposited layers (inside) behave differentially oriented compared to older (outer) layers in the dark or under FR lights, agreeing with the multinet growth hypothesis. High Ca and pectin levels were found in the cell wall of seedlings growing under blue and white light, also contributing to the low extensibility of the cell wall. Low Ca and pectin contents were found in the dark and under far-red light. Auxins marginally stimulated growth in thin cell wall circumstances. Hypocotyl growth was stimulated by gibberellins under blue light.