Identification of Relevant Phytochemical Constituents for Characterization and Authentication of Tomatoes by General Linear Model Linked to Automatic Interaction Detection (GLM-AID) and Artificial Neural Network Models (ANNs)

• Published in: PLOS ONE Vol. 10; no. 6; p. e0128566
• Main Authors: Hernández Suárez, Marcos, Astray Dopazo, Gonzalo, Larios López, Dina, Espinosa, Francisco
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science (PLoS) 15.06.2015; Public Library of Science
• Subjects: 3107.01 Producción de Cultivos; Agricultural practices; Agrochemicals; Algorithms; Artificial Neural Network Models (ANNs); Artificial neural networks; Constituents; Coumaric acid; Cultivars; Cultivo de tomates; Experimental design; Factor analysis; Feasibility studies; General Linear Model Linked to Automatic Interaction Detection (GLM-AID); Harvesting; Linear Models; Lycopersicon esculentum; Lycopersicon esculentum - chemistry; Mathematical models; Medicine; Modelo lineal general vinculado a la interacción automática de detección (GLM-AID); Models, Theoretical; Neural networks; Neural Networks, Computer; Nutrient content; p-Coumaric acid; Parameter identification; Phytochemicals; Phytochemicals - chemistry; Principal components analysis; Q; R; Redes Neuronales Artificiales (ANNs); Research Article; Science; Sensory properties; Solanum lycopersicum; Statistical analysis; Statistical methods; Tenerife; Tomates; Tomato; Tomato cultivars; Tomatoes; United States > US; Ohio; Spain
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0128566

There are a large number of tomato cultivars with a wide range of morphological, chemical, nutritional and sensorial characteristics. Many factors are known to affect the nutrient content of tomato cultivars. A complete understanding of the effect of these factors would require an exhaustive experimental design, multidisciplinary scientific approach and a suitable statistical method. Some multivariate analytical techniques such as Principal Component Analysis (PCA) or Factor Analysis (FA) have been widely applied in order to search for patterns in the behaviour and reduce the dimensionality of a data set by a new set of uncorrelated latent variables. However, in some cases it is not useful to replace the original variables with these latent variables. In this study, Automatic Interaction Detection (AID) algorithm and Artificial Neural Network (ANN) models were applied as alternative to the PCA, AF and other multivariate analytical techniques in order to identify the relevant phytochemical constituents for characterization and authentication of tomatoes. To prove the feasibility of AID algorithm and ANN models to achieve the purpose of this study, both methods were applied on a data set with twenty five chemical parameters analysed on 167 tomato samples from Tenerife (Spain). Each tomato sample was defined by three factors: cultivar, agricultural practice and harvest date. General Linear Model linked to AID (GLM-AID) tree-structured was organized into 3 levels according to the number of factors. p-Coumaric acid was the compound the allowed to distinguish the tomato samples according to the day of harvest. More than one chemical parameter was necessary to distinguish among different agricultural practices and among the tomato cultivars. Several ANN models, with 25 and 10 input variables, for the prediction of cultivar, agricultural practice and harvest date, were developed. Finally, the models with 10 input variables were chosen with fit's goodness between 44 and 100%. The lowest fits were for the cultivar classification, this low percentage suggests that other kind of chemical parameter should be used to identify tomato cultivars.