CasaLuker (Colombia)

Understanding the intricate relationship between sensory perception and physicochemical properties of cacao-based products is crucial for advancing quality control and driving product innovation. However, effectively integrating these heterogeneous data sources poses a significant challenge, particularly when sensory evaluations are derived from low-quality, subjective, and often inconsistent annotations provided by multiple experts. We propose a comprehensive framework that leverages a correlated chained Gaussian processes model for learning from crowds, termed MAR-CCGP, specifically designed for a customized Casa Luker database that integrates sensory and physicochemical data on cacao-based products. By formulating sensory evaluations as regression tasks, our approach enables the estimation of continuous perceptual scores from physicochemical inputs, while concurrently inferring the latent, input-dependent reliability of each annotator. To address the inherent noise, subjectivity, and non-stationarity in expert-generated sensory data, we introduce a three-stage methodology: (i) construction of an integrated database that unifies physicochemical parameters with corresponding sensory descriptors; (ii) application of a MAR-CCGP model to infer the underlying ground truth from noisy, crowd-sourced, and non-stationary sensory annotations; and (iii) development of a novel localized expert trustworthiness approach, also based on MAR-CCGP, which dynamically adjusts for variations in annotator consistency across the input space. Our approach provides a robust, interpretable, and scalable solution for learning from heterogeneous and noisy sensory data, establishing a principled foundation for advancing data-driven sensory analysis and product optimization in the food science domain. We validate the effectiveness of our method through a series of experiments on both semi-synthetic data and a novel real-world dataset developed in collaboration with Casa Luker, which integrates sensory evaluations with detailed physicochemical profiles of cacao-based products. Compared to state-of-the-art learning-from-crowds baselines, our framework consistently achieves superior predictive performance and more precise annotator reliability estimation, demonstrating its efficacy in multi-annotator regression settings. Of note, our unique combination of a novel database, robust noisy-data regression, and input-dependent trust scoring sets MAR-CCGP apart from existing approaches.

Flavor is the main factor driving consumers acceptance of food products. However, tracking the biochemistry of flavor is a formidable challenge due to the complexity of food composition. Current methodologies for linking individual molecules to flavor in foods and beverages are expensive and time-consuming. Predictive models based on machine learning (ML) are emerging as an alternative to speed up this process. Nonetheless, the optimal approach to predict flavor features of molecules remains elusive. In this work we present FlavorMiner, an ML-based multilabel flavor predictor. FlavorMiner seamlessly integrates different combinations of algorithms and mathematical representations, augmented with class balance strategies to address the inherent class of the input dataset. Notably, Random Forest and K-Nearest Neighbors combined with Extended Connectivity Fingerprint and RDKit molecular descriptors consistently outperform other combinations in most cases. Resampling strategies surpass weight balance methods in mitigating bias associated with class imbalance. FlavorMiner exhibits remarkable accuracy, with an average ROC AUC score of 0.88. This algorithm was used to analyze cocoa metabolomics data, unveiling its profound potential to help extract valuable insights from intricate food metabolomics data. FlavorMiner can be used for flavor mining in any food product, drawing from a diverse training dataset that spans over 934 distinct food products.