Miacro: A Reverse-Engineering Framework for Non Invasive Carcinogenic Acrylamide Removal Using Predictive Neural Networks to Rectify Industry Procedures for Sustainable, Next Generation Consumer Health
Overview
Carcinogenic acrylamide naturally forms in common foods and drinks containing asparagines and reducing sugars when processed at temperatures above 120°C. Recent worldwide concern for consumer safety measures is underway, yet, the commercial food industry has yet to discover a mitigation procedure that counteracts the majority of this Maillard reaction without altering sensory properties or presenting new health concerns. Hence, the present research focuses on developing a non-invasive removal procedure for instant coffee by exploiting acrylamide's low molecular weight and glass transition state. By properly modulating processing conditions to maximize acrylamide removal while minimizing volatile loss, I discovered the optimal thermodynamic conditions that facilitate the sublimation, and thus, removal of water content and the majority of acrylamide concentration from instant coffee. A novel reverse engineering framework is developed using various regression models trained after experimentation with several hundred LC/MS/MS results. Repeated experiments validated proposed calculations with remarkable predictive capability as R2 = 98.2% of the variance for calculated removal values are accounted for. Such results elucidate the requirements for scaling the method to industrial instant coffee manufacturing procedures. The Miacro framework can search for the optimal processing parameters that satisfy a target acrylamide removal specification for the industrial freeze-drying phase.
Competition history
- ISEF 2019
Resources
Related projects
ISEF · 2026
Colorimetric Arsenic Detection at Micromolar Concentrations and Machine Learning Assisted Development of a Composite Teabag for Arsenic Bioremediation in Drinking Water
ISEF · 2025
Unraveling Molecular Carcinogenicity Through Computational Insights
ISEF · 2016
A Smart Burn and Spill Proof “SAFE” Microwave that Spares the Salad: Novel Application of Levenberg-Marquardt Algorithms in Bayesian Analysis for Real-Time Numerical Thermodynamic Modeling
ISEF · 2022
CarbNN: A Novel Active Transfer Learning Neural Network to Build De Novo Metal Organic Frameworks (MOFs) for Carbon Capture
ISEF · 2024
AP Using Machine Learning Algorithms To Predict Whether Phytochemicals Are Cancerous or Anti-Cancerous
ISEF · 2023
A Novel Adversarial Autoencoder With Latent-Based Optimization to Design De-Novo Ionic Liquids for Post-Combustion Carbon Capture
ISEF · 2025
Novel Alternative Method to Improve the Safety and Targeting of Nanotherapeutics
ISEF · 2026
Developing a Rapid Screening Approach for Milk Counterfeiting Risks Using Infrared Spectroscopy Combined With Chemometrics
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: Regeneron International Science and Engineering Fair