Discovery of food identity markers by metabolomics and machine learning technology

Alexander Erban,Veronica Baroni,Daniel Wunderlin,Joachim Kopka,Agustín Lucini Más,Federico Brigante,Federico Martinez-Seidel,Ines Fehrle

doi:10.1038/s41598-019-46113-y

Abstract

Verification of food authenticity establishes consumer trust in food ingredients and components of processed food. Next to genetic or protein markers, chemicals are unique identifiers of food components. Non-targeted metabolomics is ideally suited to screen food markers when coupled to efficient data analysis. This study explored feasibility of random forest (RF) machine learning, specifically its inherent feature extraction for non-targeted metabolic marker discovery. The distinction of chia, linseed, and sesame that have gained attention as “superfoods” served as test case. Chemical fractions of non-processed seeds and of wheat cookies with seed ingredients were profiled. RF technology classified original seeds unambiguously but appeared overdesigned for material with unique secondary metabolites, like sesamol or rosmarinic acid in the Lamiaceae, chia. Most unique metabolites were diluted or lost during cookie production but RF technology classified the presence of the seed ingredients in cookies with 6.7% overall error and revealed food processing markers, like 4-hydroxybenzaldehyde for chia and succinic acid monomethylester for linseed additions. RF based feature extraction was adequate for difficult classifications but marker selection should not be without human supervision. Combination with alternative data analysis technologies is advised and further testing of a wide range of seeds and food processing methods.

Highlights

Food authenticity and nutritional quality are of great interest to the food industry, producers, distributors, and consumer trust in nutritional value, origin, and production processes[1,2]
All seed batches were free of contaminations according to visual inspection (Fig. 1A) and, except a single sesame sample (S-20), contained seed coats to account for the fact that processed food material often contains complete seeds
Our study demonstrates that machine learning technology may support marker search, here the search for markers of food integrity as exemplified by the test case of three seed types that are media-hyped as superfood additions to diverse processed food materials

Summary

Introduction

Food authenticity and nutritional quality are of great interest to the food industry, producers, distributors, and consumer trust in nutritional value, origin, and production processes[1,2]. If combined with hydrolysis procedures, the amino acid composition, fatty acid content and carbohydrate composition of proteins, fats and polysaccharides can be determined This information is indispensable to both consumers and food producers that take interest in potential health benefits and www.nature.com/scientificreports/. The large diversity of primary and specialized secondary metabolites makes plant-based food and food additives highly amenable to the search for metabolic markers of food authenticity or nutritional quality. Linseed (flax, Linum usitatissimum L.) and sesame (Sesamum indicum L.) are more traditional, highly nutritive seeds[33,34,35] These seeds, like chia seeds, are used in bread and bakery products to improve both nutritional characteristics and consumers acceptance. Marketing as “superfoods” and resulting consumer interest turned chia seeds into a high value food ingredient that may become a target of fraud and adulteration. Knowledge of differentiating seed markers will benefit both manufacturers and consumers by providing means of authenticating the presence of high value seed ingredients in non-processed and processed food

Methods

Results

Conclusion