Anastasiadi, MariaMohareb, Fady R.Redfern, Sally P.Berry, MarkSimmonds, MoniqueTerry, Leon A.2017-06-142017-06-142017-06-02Maria Anastasiadi, Fady R Mohareb, Sally P. Redfern, et al., Biochemical profile of heritage and modern apple cultivars and application of machine learning methods to predict usage, age, and harvest season. Journal of Agricultural and Food Chemistry, 2017, Vol. 65, Issue 26, pp. 5339-53560021-8561http://dx.doi.org/10.1021/acs.jafc.7b00500http://dspace.lib.cranfield.ac.uk/handle/1826/12021The present study represents the first major attempt to characterise the biochemical profile in different tissues of a large selection of apple cultivars sourced from the UK’s National Fruit Collection comprising dessert, ornamental, cider and culinary apples. Furthermore, advanced Machine Learning methods were applied with the objective to identify whether the phenolic and sugar composition of an apple cultivar could be used as a biomarker fingerprint to differentiate between heritage and mainstream commercial cultivars as well as govern the separation among primary usage groups and harvest season. Prediction accuracy > 90% was achieved with Random Forest for all three models. The results highlighted the extraordinary phytochemical potency and unique profile of some heritage, cider and ornamental apple cultivars, especially in comparison to more mainstream apple cultivars. Therefore, these findings could guide future cultivar selection on the basis of health-promoting phytochemical content.enAttribution-NonCommercial 4.0 InternationalMalusphenolic compoundssugarsorganic acidsamygdalinpredictive modellingArticle17719186