Machine Learning-Mediated Ultrasensitive Detection of Citrinin and Associated Mycotoxins in Real Food Samples Discerned from a Photoluminescent Carbon Dot Barcode Array.

Abstract

Economically viable remote sensing of foodborne contaminants using minimalistic chemical reagents and simultaneous automation calls for a concrete integration of a chemical detection strategy with artificial intelligence. In a first of its kind, we report the ultrasensitive detection of citrinin and associated mycotoxins like aflatoxin B1 and ochratoxin A using an Alizarin Red S (ARS) and cystamine-derived carbon dot (CD) that aptly amalgamate with machine learning algorithms for automation. The photoluminescence response of the CD as a function of various solvents and pH is used to generate array channels that are further modulated in the presence of the mycotoxins whose digital images were acquired to determine pixelation, essentially creating a barcode. The barcode was fed to machine learning algorithms that actualize and intertwine convoluted databases, demonstrating Extreme Gradient Boosting (XGBoost) as the optimized model out of eight algorithms tested. Spiked samples of wheat, rice, gram, maize, coffee, and milk were used to evaluate the testing model where an exemplary accuracy of 100% even at 10 pmol of mycotoxin concentration was achieved. Most importantly, the coexistence of mycotoxins could also be detected through the CD array and XGBoost synergy hinting toward a broader scope of the developed methodology for smart detection of foodborne contaminants.